Data set terminology of deep learning in medicine: a historical review and recommendation.

Medicine and deep learning-based artificial intelligence (AI) engineering represent two distinct fields each with decades of published history. The current rapid convergence of deep learning and medicine has led to significant advancements, yet it has also introduced ambiguity regarding data set terms common to both fields, potentially leading to miscommunication and methodological discrepancies. This narrative review aims to give historical context for these terms, accentuate the importance of clarity when these terms are used in medical deep learning contexts, and offer solutions to mitigate misunderstandings by readers from either field. Through an examination of historical documents, including articles, writing guidelines, and textbooks, this review traces the divergent evolution of terms for data sets and their impact. Initially, the discordant interpretations of the word 'validation' in medical and AI contexts are explored. We then show that in the medical field as well, terms traditionally used in the deep learning domain are becoming more common, with the data for creating models referred to as the 'training set', the data for tuning of parameters referred to as the 'validation (or tuning) set', and the data for the evaluation of models as the 'test set'. Additionally, the test sets used for model evaluation are classified into internal (random splitting, cross-validation, and leave-one-out) sets and external (temporal and geographic) sets. This review then identifies often misunderstood terms and proposes pragmatic solutions to mitigate terminological confusion in the field of deep learning in medicine. We support the accurate and standardized description of these data sets and the explicit definition of data set splitting terminologies in each publication. These are crucial methods for demonstrating the robustness and generalizability of deep learning applications in medicine. This review aspires to enhance the precision of communication, thereby fostering more effective and transparent research methodologies in this interdisciplinary field.

Comparing the Diagnostic Performance of GPT-4-based ChatGPT, GPT-4V-based ChatGPT, and Radiologists in Challenging Neuroradiology Cases.

PURPOSE: To compare the diagnostic performance among Generative Pre-trained Transformer (GPT)-4-based ChatGPT, GPT­4 with vision (GPT-4V) based ChatGPT, and radiologists in challenging neuroradiology cases. METHODS: We collected 32 consecutive "Freiburg Neuropathology Case Conference" cases from the journal Clinical Neuroradiology between March 2016 and December 2023. We input the medical history and imaging findings into GPT-4-based ChatGPT and the medical history and images into GPT-4V-based ChatGPT, then both generated a diagnosis for each case. Six radiologists (three radiology residents and three board-certified radiologists) independently reviewed all cases and provided diagnoses. ChatGPT and radiologists' diagnostic accuracy rates were evaluated based on the published ground truth. Chi-square tests were performed to compare the diagnostic accuracy of GPT-4-based ChatGPT, GPT-4V-based ChatGPT, and radiologists. RESULTS: GPT­4 and GPT-4V-based ChatGPTs achieved accuracy rates of 22% (7/32) and 16% (5/32), respectively. Radiologists achieved the following accuracy rates: three radiology residents 28% (9/32), 31% (10/32), and 28% (9/32); and three board-certified radiologists 38% (12/32), 47% (15/32), and 44% (14/32). GPT-4-based ChatGPT's diagnostic accuracy was lower than each radiologist, although not significantly (all p > 0.07). GPT-4V-based ChatGPT's diagnostic accuracy was also lower than each radiologist and significantly lower than two board-certified radiologists (p = 0.02 and 0.03) (not significant for radiology residents and one board-certified radiologist [all p > 0.09]). CONCLUSION: While GPT-4-based ChatGPT demonstrated relatively higher diagnostic performance than GPT-4V-based ChatGPT, the diagnostic performance of GPT­4 and GPT-4V-based ChatGPTs did not reach the performance level of either radiology residents or board-certified radiologists in challenging neuroradiology cases.

Percutaneous transhepatic sclerotherapy for ascending colonic varices due to left-sided portal hypertension.

Left-sided portal hypertension (LSPH) causes varices and splenomegaly due to splenic vein issues. Colonic varices are rare and lack standardized treatment. We report the successful treatment of colonic varices caused by LSPH, by addressing both the afferent and efferent veins. A 70-year-old man with distal cholangiocarcinoma had surgery without splenic vein resection, leading to proximal splenic vein stenosis and varices at multiple locations. Percutaneous transhepatic splenic venography revealed that collateral veins flowed into the ascending colonic varices and returned to the portal vein. Complete thrombosis of the varices was achieved by injecting sclerosants and placing coils in both the afferent and efferent veins. The procedure was safe and effective, with no variceal recurrence. This approach provides a minimally invasive option for treating colonic varices associated with LSPH.

Deep learning-based diffusion tensor image generation model: a proof-of-concept study.

This study created an image-to-image translation model that synthesizes diffusion tensor images (DTI) from conventional diffusion weighted images, and validated the similarities between the original and synthetic DTI. Thirty-two healthy volunteers were prospectively recruited. DTI and DWI were obtained with six and three directions of the motion probing gradient (MPG), respectively. The identical imaging plane was paired for the image-to-image translation model that synthesized one direction of the MPG from DWI. This process was repeated six times in the respective MPG directions. Regions of interest (ROIs) in the lentiform nucleus, thalamus, posterior limb of the internal capsule, posterior thalamic radiation, and splenium of the corpus callosum were created and applied to maps derived from the original and synthetic DTI. The mean values and signal-to-noise ratio (SNR) of the original and synthetic maps for each ROI were compared. The Bland-Altman plot between the original and synthetic data was evaluated. Although the test dataset showed a larger standard deviation of all values and lower SNR in the synthetic data than in the original data, the Bland-Altman plots showed each plot localizing in a similar distribution. Synthetic DTI could be generated from conventional DWI with an image-to-image translation model.

Evaluation of cranial nerve involvement in chordomas and chondrosarcomas: a retrospective imaging study.

PURPOSE: Cranial nerve involvement (CNI) influences the treatment strategies and prognosis of head and neck tumors. However, its incidence in skull base chordomas and chondrosarcomas remains to be investigated. This study evaluated the imaging features of chordoma and chondrosarcoma, with a focus on the differences in CNI. METHODS: Forty-two patients (26 and 16 patients with chordomas and chondrosarcomas, respectively) treated at our institution between January 2007 and January 2023 were included in this retrospective study. Imaging features, such as the maximum diameter, tumor location (midline or off-midline), calcification, signal intensity on T2-weighted image, mean apparent diffusion coefficient (ADC) values, contrast enhancement, and CNI, were evaluated and compared using Fisher's exact test or the Mann-Whitney U-test. The odds ratio (OR) was calculated to evaluate the association between the histological type and imaging features. RESULTS: The incidence of CNI in chondrosarcomas was significantly higher than that in chordomas (63% vs. 8%, P < 0.001). An off-midline location was more common in chondrosarcomas than in chordomas (86% vs. 13%; P < 0.001). The mean ADC values of chondrosarcomas were significantly higher than those of chordomas (P < 0.001). Significant associations were identified between chondrosarcomas and CNI (OR = 20.00; P < 0.001), location (OR = 53.70; P < 0.001), and mean ADC values (OR = 1.01; P = 0.002). CONCLUSION: The incidence of CNI and off-midline location in chondrosarcomas was significantly higher than that in chordomas. CNI, tumor location, and the mean ADC can help distinguish between these entities.

Accuracy of ChatGPT generated diagnosis from patient's medical history and imaging findings in neuroradiology cases.

PURPOSE: The noteworthy performance of Chat Generative Pre-trained Transformer (ChatGPT), an artificial intelligence text generation model based on the GPT-4 architecture, has been demonstrated in various fields; however, its potential applications in neuroradiology remain unexplored. This study aimed to evaluate the diagnostic performance of GPT-4 based ChatGPT in neuroradiology. METHODS: We collected 100 consecutive "Case of the Week" cases from the American Journal of Neuroradiology between October 2021 and September 2023. ChatGPT generated a diagnosis from patient's medical history and imaging findings for each case. Then the diagnostic accuracy rate was determined using the published ground truth. Each case was categorized by anatomical location (brain, spine, and head & neck), and brain cases were further divided into central nervous system (CNS) tumor and non-CNS tumor groups. Fisher's exact test was conducted to compare the accuracy rates among the three anatomical locations, as well as between the CNS tumor and non-CNS tumor groups. RESULTS: ChatGPT achieved a diagnostic accuracy rate of 50% (50/100 cases). There were no significant differences between the accuracy rates of the three anatomical locations (p = 0.89). The accuracy rate was significantly lower for the CNS tumor group compared to the non-CNS tumor group in the brain cases (16% [3/19] vs. 62% [36/58], p < 0.001). CONCLUSION: This study demonstrated the diagnostic performance of ChatGPT in neuroradiology. ChatGPT's diagnostic accuracy varied depending on disease etiologies, and its diagnostic accuracy was significantly lower in CNS tumors compared to non-CNS tumors.

Afferent vein embolization via retrograde approach as a potential treatment strategy for bleeding duodenal varices.

The standard treatment for ruptured duodenal varices remains to be established. Emergency balloon-occluded retrograde transvenous obliteration is challenging in patients with bleeding because re-rupture of varices can occur due to increased pressure when using the retrograde approach. Herein, we describe a case in which a catheter was retrogradely advanced to the afferent vein beyond bleeding duodenal varices; however, the varices re-ruptured during coil embolization, and a part of the catheter was deviated into the intestinal tract. The rupture site was embolized by liquid embolic materials from the microcatheter. Embolization via retrograde approach needs to be carefully performed.

Chest radiography as a biomarker of ageing: artificial intelligence-based, multi-institutional model development and validation in Japan.

BACKGROUND: Chest radiographs are widely available and cost-effective; however, their usefulness as a biomarker of ageing using multi-institutional data remains underexplored. The aim of this study was to develop a biomarker of ageing from chest radiography and examine the correlation between the biomarker and diseases. METHODS: In this retrospective, multi-institutional study, we trained, tuned, and externally tested an artificial intelligence (AI) model to estimate the age of healthy individuals using chest radiographs as a biomarker. For the biomarker modelling phase of the study, we used healthy chest radiographs consecutively collected between May 22, 2008, and Dec 28, 2021, from three institutions in Japan. Data from two institutions were used for training, tuning, and internal testing, and data from the third institution were used for external testing. To evaluate the performance of the AI model in estimating ages, we calculated the correlation coefficient, mean square error, root mean square error, and mean absolute error. The correlation investigation phase of the study included chest radiographs from individuals with a known disease that were consecutively collected between Jan 1, 2018, and Dec 31, 2021, from an additional two institutions in Japan. We investigated the odds ratios (ORs) for various diseases given the difference between the AI-estimated age and chronological age (ie, the difference-age). FINDINGS: We included 101 296 chest radiographs from 70 248 participants across five institutions. In the biomarker modelling phase, the external test dataset from 3467 healthy participants included 8046 radiographs. Between the AI-estimated age and chronological age, the correlation coefficient was 0·95 (99% CI 0·95-0·95), the mean square error was 15·0 years (99% CI 14·0-15·0), the root mean square error was 3·8 years (99% CI 3·8-3·9), and the mean absolute error was 3·0 years (99% CI 3·0-3·1). In the correlation investigation phase, the external test datasets from 34 197 participants with a known disease included 34 197 radiographs. The ORs for difference-age were as follows: 1·04 (99% CI 1·04-1·05) for hypertension; 1·02 (1·01-1·03) for hyperuricaemia; 1·05 (1·03-1·06) for chronic obstructive pulmonary disease; 1·08 (1·06-1·09) for interstitial lung disease; 1·05 (1·03-1·06) for chronic renal failure; 1·04 (1·03-1·06) for atrial fibrillation; 1·03 (1·02-1·04) for osteoporosis; and 1·05 (1·03-1·06) for liver cirrhosis. INTERPRETATION: The AI-estimated age using chest radiographs showed a strong correlation with chronological age in the healthy cohorts. Furthermore, in cohorts of individuals with known diseases, the difference between estimated age and chronological age correlated with various chronic diseases. The use of this biomarker might pave the way for enhanced risk stratification methodologies, individualised therapeutic interventions, and innovative early diagnostic and preventive approaches towards age-associated pathologies. FUNDING: None. TRANSLATION: For the Japanese translation of the abstract see Supplementary Materials section.

AI-based Virtual Synthesis of Methionine PET from Contrast-enhanced MRI: Development and External Validation Study.

Background Carbon 11 (11C)-methionine is a useful PET radiotracer for the management of patients with glioma, but radiation exposure and lack of molecular imaging facilities limit its use. Purpose To generate synthetic methionine PET images from contrast-enhanced (CE) MRI through an artificial intelligence (AI)-based image-to-image translation model and to compare its performance for grading and prognosis of gliomas with that of real PET. Materials and Methods An AI-based model to generate synthetic methionine PET images from CE MRI was developed and validated from patients who underwent both methionine PET and CE MRI at a university hospital from January 2007 to December 2018 (institutional data set). Pearson correlation coefficients for the maximum and mean tumor to background ratio (TBRmax and TBRmean, respectively) of methionine uptake and the lesion volume between synthetic and real PET were calculated. Two additional open-source glioma databases of preoperative CE MRI without methionine PET were used as the external test set. Using the TBRs, the area under the receiver operating characteristic curve (AUC) for classifying high-grade and low-grade gliomas and overall survival were evaluated. Results The institutional data set included 362 patients (mean age, 49 years ± 19 [SD]; 195 female, 167 male; training, n = 294; validation, n = 34; test, n = 34). In the internal test set, Pearson correlation coefficients were 0.68 (95% CI: 0.47, 0.81), 0.76 (95% CI: 0.59, 0.86), and 0.92 (95% CI: 0.85, 0.95) for TBRmax, TBRmean, and lesion volume, respectively. The external test set included 344 patients with gliomas (mean age, 53 years ± 15; 192 male, 152 female; high grade, n = 269). The AUC for TBRmax was 0.81 (95% CI: 0.75, 0.86) and the overall survival analysis showed a significant difference between the high (2-year survival rate, 27%) and low (2-year survival rate, 71%; P < .001) TBRmax groups. Conclusion The AI-based model-generated synthetic methionine PET images strongly correlated with real PET images and showed good performance for glioma grading and prognostication. Published under a CC BY 4.0 license. Supplemental material is available for this article.

Atezolizumab plus bevacizumab-induced intratumoral hemorrhage in a patient with rib metastasis from unresectable hepatocellular carcinoma.

Recently, combination therapy with atezolizumab, a humanized monoclonal antiprogrammed death ligand-1 antibody, and bevacizumab, has become available for treatment of unresectable hepatocellular carcinoma (HCC). We herein report a 73-year-old man with advanced stage HCC who developed fatigue during treatment with atezolizumab-bevacizumab combination therapy. Computed tomography identified intratumoral hemorrhage within the HCC metastasis to the right fifth rib metastasis of HCC, which was confirmed on emergency angiography of the right 4th and 5th intercostal arteries and some branches of the subclavian artery confirmed intratumoral hemorrhage, following which transcatheter arterial embolization (TAE) was performed to achieve hemostasis. He continued to receive atezolizumab-bevacizumab combination therapy after TAE, and no rebleeding was seen. Although uncommon, rupture and intratumoral hemorrhage in the HCC metastasis to the ribs can cause life-threatening hemothorax. However, to our knowledge, no previous cases of intratumoral hemorrhage in HCC during atezolizumab-bevacizumab combination therapy have been reported. This is the first report of intratumoral hemorrhage with the combination therapy of atezolizumab and bevacizumab, which was successfully controlled by TAE. Patients receiving this combination therapy should be observed for intratumoral hemorrhage, which can be managed by TAE if it does occur.

Deep learning for pneumothorax diagnosis: a systematic review and meta-analysis.

BACKGROUND: Deep learning (DL), a subset of artificial intelligence (AI), has been applied to pneumothorax diagnosis to aid physician diagnosis, but no meta-analysis has been performed. METHODS: A search of multiple electronic databases through September 2022 was performed to identify studies that applied DL for pneumothorax diagnosis using imaging. Meta-analysis via a hierarchical model to calculate the summary area under the curve (AUC) and pooled sensitivity and specificity for both DL and physicians was performed. Risk of bias was assessed using a modified Prediction Model Study Risk of Bias Assessment Tool. RESULTS: In 56 of the 63 primary studies, pneumothorax was identified from chest radiography. The total AUC was 0.97 (95% CI 0.96-0.98) for both DL and physicians. The total pooled sensitivity was 84% (95% CI 79-89%) for DL and 85% (95% CI 73-92%) for physicians and the pooled specificity was 96% (95% CI 94-98%) for DL and 98% (95% CI 95-99%) for physicians. More than half of the original studies (57%) had a high risk of bias. CONCLUSIONS: Our review found the diagnostic performance of DL models was similar to that of physicians, although the majority of studies had a high risk of bias. Further pneumothorax AI research is needed.

Artificial intelligence-based detection of atrial fibrillation from chest radiographs.

OBJECTIVE: The purpose of this study was to develop an artificial intelligence (AI)-based model to detect features of atrial fibrillation (AF) on chest radiographs. METHODS: This retrospective study included consecutively collected chest radiographs of patients who had echocardiography at our institution from July 2016 to May 2019. Eligible radiographs had been acquired within 30 days of the echocardiography. These radiographs were labeled as AF-positive or AF-negative based on the associated electronic medical records; then, each patient was randomly divided into training, validation, and test datasets in an 8:1:1 ratio. A deep learning-based model to classify radiographs as with or without AF was trained on the training dataset, tuned with the validation dataset, and evaluated with the test dataset. RESULTS: The training dataset included 11,105 images (5637 patients; 3145 male, mean age ± standard deviation, 68 ± 14 years), the validation dataset included 1388 images (704 patients, 397 male, 67 ± 14 years), and the test dataset included 1375 images (706 patients, 395 male, 68 ± 15 years). Applying the model to the validation and test datasets gave a respective area under the curve of 0.81 (95% confidence interval, 0.78-0.85) and 0.80 (0.76-0.84), sensitivity of 0.76 (0.70-0.81) and 0.70 (0.64-0.76), specificity of 0.75 (0.72-0.77) and 0.74 (0.72-0.77), and accuracy of 0.75 (0.72-0.77) and 0.74 (0.71-0.76). CONCLUSION: Our AI can identify AF on chest radiographs, which provides a new way for radiologists to infer AF. KEY POINTS: • A deep learning-based model was trained to detect atrial fibrillation in chest radiographs, showing that there are indicators of atrial fibrillation visible even on static images. • The validation and test datasets each gave a solid performance with area under the curve, sensitivity, and specificity of 0.81, 0.76, and 0.75, respectively, for the validation dataset, and 0.80, 0.70, and 0.74, respectively, for the test dataset. • The saliency maps highlighted anatomical areas consistent with those reported for atrial fibrillation on chest radiographs, such as the atria.

Orbital apex schwannoma with a high titer of proteinase 3 antineutrophil cytoplasmic antibody.

Here, we present a very unusual case of orbital apex schwannoma with a high titer of proteinase 3 antineutrophil cytoplasmic antibody (PR3-ANCA). A 67-year-old man presented with a 3-month history of double vision. Radiological examinations revealed a mass lesion at the left orbital apex, and laboratory examination revealed a high titer of PR3-ANCA, of 49.1 U/mL (reference range<2.0). After the surgery, the lesion was histologically diagnosed as schwannoma, and the PR3-ANCA titer decreased to 8.4 U/m. Although making a correct diagnosis of orbital apex schwannoma may be difficult due to the need to differentiate from granulomatosis with polyangiitis when PR3-ANCA serum levels are elevated, careful examination of the radiological findings may aid the diagnosis.

[Sustained Complete Remission after Eradication Therapy in A Helicobacter pylori-Negative Cecum Mucosa-Associated Lymphoid Tissue Lymphoma].

Most primary gastric mucosa-associated lymphoid tissue(MALT)lymphomas are associated with a chronic Helicobacter pylori(H. pylori)infection. The eradication of H. pylori is the first-line treatment for H. pylori-positive cases with early-stage disease. In addition, successful treatment of H. pylori-negative early stage MALT lymphomas by eradication has been reported in several small cases series. However, the association of primary gastrointestinal MALT lymphomas with H. pylori in areas other than the stomach is not clear, and the efficacy of eradication therapy for these patients has not been established. We performed H. pylori eradication therapy for H. pylori-negative cecum MALT lymphoma. Three months later, a histopathological examination showed no evidence of MALT lymphoma, and the patient was classified as being in remission. So far, the patient has been in remission for 1 year and 6 months. Our case is the first report of successfully treating H. pylori- negative cecum MALT lymphoma with eradication therapy.