Artificial intelligence for automated detection and measurements of carpal instability signs on conventional radiographs.

OBJECTIVES: To develop and validate an artificial intelligence (AI) system for measuring and detecting signs of carpal instability on conventional radiographs. MATERIALS AND METHODS: Two case-control datasets of hand and wrist radiographs were retrospectively acquired at three hospitals (hospitals A, B, and C). Dataset 1 (2178 radiographs from 1993 patients, hospitals A and B, 2018-2019) was used for developing an AI system for measuring scapholunate (SL) joint distances, SL and capitolunate (CL) angles, and carpal arc interruptions. Dataset 2 (481 radiographs from 217 patients, hospital C, 2017-2021) was used for testing, and with a subsample (174 radiographs from 87 patients), an observer study was conducted to compare its performance to five clinicians. Evaluation metrics included mean absolute error (MAE), sensitivity, and specificity. RESULTS: Dataset 2 included 258 SL distances, 189 SL angles, 191 CL angles, and 217 carpal arc labels obtained from 217 patients (mean age, 51 years ± 23 [standard deviation]; 133 women). The MAE in measuring SL distances, SL angles, and CL angles was respectively 0.65 mm (95%CI: 0.59, 0.72), 7.9 degrees (95%CI: 7.0, 8.9), and 5.9 degrees (95%CI: 5.2, 6.6). The sensitivity and specificity for detecting arc interruptions were 83% (95%CI: 74, 91) and 64% (95%CI: 56, 71). The measurements were largely comparable to those of the clinicians, while arc interruption detections were more accurate than those of most clinicians. CONCLUSION: This study demonstrates that a newly developed automated AI system accurately measures and detects signs of carpal instability on conventional radiographs. CLINICAL RELEVANCE STATEMENT: This system has the potential to improve detections of carpal arc interruptions and could be a promising tool for supporting clinicians in detecting carpal instability.

Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction.

Background Multiple commercial artificial intelligence (AI) products exist for assessing radiographs; however, comparable performance data for these algorithms are limited. Purpose To perform an independent, stand-alone validation of commercially available AI products for bone age prediction based on hand radiographs and lung nodule detection on chest radiographs. Materials and Methods This retrospective study was carried out as part of Project AIR. Nine of 17 eligible AI products were validated on data from seven Dutch hospitals. For bone age prediction, the root mean square error (RMSE) and Pearson correlation coefficient were computed. The reference standard was set by three to five expert readers. For lung nodule detection, the area under the receiver operating characteristic curve (AUC) was computed. The reference standard was set by a chest radiologist based on CT. Randomized subsets of hand (n = 95) and chest (n = 140) radiographs were read by 14 and 17 human readers, respectively, with varying experience. Results Two bone age prediction algorithms were tested on hand radiographs (from January 2017 to January 2022) in 326 patients (mean age, 10 years ± 4 [SD]; 173 female patients) and correlated strongly with the reference standard (r = 0.99; P < .001 for both). No difference in RMSE was observed between algorithms (0.63 years [95% CI: 0.58, 0.69] and 0.57 years [95% CI: 0.52, 0.61]) and readers (0.68 years [95% CI: 0.64, 0.73]). Seven lung nodule detection algorithms were validated on chest radiographs (from January 2012 to May 2022) in 386 patients (mean age, 64 years ± 11; 223 male patients). Compared with readers (mean AUC, 0.81 [95% CI: 0.77, 0.85]), four algorithms performed better (AUC range, 0.86-0.93; P value range, <.001 to .04). Conclusions Compared with human readers, four AI algorithms for detecting lung nodules on chest radiographs showed improved performance, whereas the remaining algorithms tested showed no evidence of a difference in performance. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Omoumi and Richiardi in this issue.

Musculoskeletal radiologist-level performance by using deep learning for detection of scaphoid fractures on conventional multi-view radiographs of hand and wrist.

OBJECTIVES: To assess how an artificial intelligence (AI) algorithm performs against five experienced musculoskeletal radiologists in diagnosing scaphoid fractures and whether it aids their diagnosis on conventional multi-view radiographs. METHODS: Four datasets of conventional hand, wrist, and scaphoid radiographs were retrospectively acquired at two hospitals (hospitals A and B). Dataset 1 (12,990 radiographs from 3353 patients, hospital A) and dataset 2 (1117 radiographs from 394 patients, hospital B) were used for training and testing a scaphoid localization and laterality classification component. Dataset 3 (4316 radiographs from 840 patients, hospital A) and dataset 4 (688 radiographs from 209 patients, hospital B) were used for training and testing the fracture detector. The algorithm was compared with the radiologists in an observer study. Evaluation metrics included sensitivity, specificity, positive predictive value (PPV), area under the characteristic operating curve (AUC), Cohen's kappa coefficient (κ), fracture localization precision, and reading time. RESULTS: The algorithm detected scaphoid fractures with a sensitivity of 72%, specificity of 93%, PPV of 81%, and AUC of 0.88. The AUC of the algorithm did not differ from each radiologist (0.87 [radiologists' mean], p ≥ .05). AI assistance improved five out of ten pairs of inter-observer Cohen's κ agreements (p < .05) and reduced reading time in four radiologists (p < .001), but did not improve other metrics in the majority of radiologists (p ≥ .05). CONCLUSIONS: The AI algorithm detects scaphoid fractures on conventional multi-view radiographs at the level of five experienced musculoskeletal radiologists and could significantly shorten their reading time. KEY POINTS: • An artificial intelligence algorithm automatically detects scaphoid fractures on conventional multi-view radiographs at the same level of five experienced musculoskeletal radiologists. • There is preliminary evidence that automated scaphoid fracture detection can significantly shorten the reading time of musculoskeletal radiologists.

Development and Validation of a Convolutional Neural Network for Automated Detection of Scaphoid Fractures on Conventional Radiographs.

PURPOSE: To compare the performance of a convolutional neural network (CNN) to that of 11 radiologists in detecting scaphoid bone fractures on conventional radiographs of the hand, wrist, and scaphoid. MATERIALS AND METHODS: At two hospitals (hospitals A and B), three datasets consisting of conventional hand, wrist, and scaphoid radiographs were retrospectively retrieved: a dataset of 1039 radiographs (775 patients [mean age, 48 years ± 23 {standard deviation}; 505 female patients], period: 2017-2019, hospitals A and B) for developing a scaphoid segmentation CNN, a dataset of 3000 radiographs (1846 patients [mean age, 42 years ± 22; 937 female patients], period: 2003-2019, hospital B) for developing a scaphoid fracture detection CNN, and a dataset of 190 radiographs (190 patients [mean age, 43 years ± 20; 77 female patients], period: 2011-2020, hospital A) for testing the complete fracture detection system. Both CNNs were applied consecutively: The segmentation CNN localized the scaphoid and then passed the relevant region to the detection CNN for fracture detection. In an observer study, the performance of the system was compared with that of 11 radiologists. Evaluation metrics included the Dice similarity coefficient (DSC), Hausdorff distance (HD), sensitivity, specificity, positive predictive value (PPV), and area under the receiver operating characteristic curve (AUC). RESULTS: The segmentation CNN achieved a DSC of 97.4% ± 1.4 with an HD of 1.31 mm ± 1.03. The detection CNN had sensitivity of 78% (95% CI: 70, 86), specificity of 84% (95% CI: 77, 92), PPV of 83% (95% CI: 77, 90), and AUC of 0.87 (95% CI: 0.81, 0.91). There was no difference between the AUC of the CNN and that of the radiologists (0.87 [95% CI: 0.81, 0.91] vs 0.83 [radiologist range: 0.79-0.85]; P = .09). CONCLUSION: The developed CNN achieved radiologist-level performance in detecting scaphoid bone fractures on conventional radiographs of the hand, wrist, and scaphoid.Keywords: Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms, Feature Detection-Vision-Application Domain, Computer-Aided DiagnosisSee also the commentary by Li and Torriani in this issue.Supplemental material is available for this article.©RSNA, 2021.

Cecal volvulus caused by a large uterine leiomyoma.

INTRODUCTION: Cecal volvulus is a relatively uncommon encountered clinical condition. PRESENTATION OF CASE: A 48-year-old patient known with a large uterine leiomyoma, presented with progressive abdominal pain since one week. An abdominal computed tomography scan revealed a very large leiomyoma of the uterus, severely distended loops of the small bowel with a caliber change and a suggested 'whirl sign' of the mesenteric vessels. A laparotomy was performed, showing a very large uterus as well as torsion of the mesentery of the cecum with a sharp demarcated area of necrosis of the right hemicolon. DISCUSSION: Cecal volvulus due to a large uterine mass is a rare encountered clinical entity. The suggested mechanism might be the same mechanism causing cecal volvulus during pregnancy; the enlarged uterus raisingout the mobile cecum out of the pelvis. Obstruction may occur from kinking of the colon at a fixed point. CONCLUSION: This case demonstrates that uterine leiomyoma can be a cause of a cecal volvulus, leading to severe intestinal strangulation.

Glenohumeral joint injection: a comparative study of ultrasound and fluoroscopically guided techniques before MR arthrography.

To assess the variability in accuracy of contrast media introduction, leakage, required time and patient discomfort in four different centres, each using a different image-guided glenohumeral injection technique. Each centre included 25 consecutive patients. The ultrasound-guided anterior (USa) and posterior approach (USp), fluoroscopic-guided anterior (FLa) and posterior (FLp) approach were used. Number of injection attempts, effect of contrast leakage on diagnostic quality, and total room, radiologist and procedure times were measured. Pain was documented with a visual analogue scale (VAS) pain score. Access to the joint was achieved in all patients. A successful first attempt significantly occurred more often with US (94%) than with fluoroscopic guidance (72%). Leakage of contrast medium did not cause interpretative difficulties. With US guidance mean room, procedure and radiologist times were significantly shorter (p < 0.001). The USa approach was rated with the lowest pre- and post-injection VAS scores. The four image-guided injection techniques are successful in injection of contrast material into the glenohumeral joint. US-guided injections and especially the anterior approach are significantly less time consuming, more successful on the first attempt, cause less patient discomfort and obviate the need for radiation and iodine contrast.

Injection of the subacromial-subdeltoid bursa: blind or ultrasound-guided?

BACKGROUND: Blind injection of the subacromial-sub-deltoid bursa (SSB) for diagnostic purposes (Neer test) or therapeutic purposes (corticosteroid therapy) is frequently used. Poor response to previous blind injection or side effects may be due to a misplaced injection. It is assumed that ultrasound (US)-guided injections are more accurate than blind injections. In a randomized study, we compared the accuracy of blind injection to that of US-guided injection into the SSB. PATIENTS AND METHODS: 20 consecutive patients with impingement syndrome of the shoulder were randomized for blind or US-guided injection in the SSB. Injection was performed either by an experienced orthopedic surgeon or by an experienced musculoskeletal radiologist. A mixture of 1 m'L methylprednisolone acetate, 4 mL prilocaine hydrochloride and 0.02 mL (0.01 mmol) Gadolinium DTPA was injected. Immediately after injection, a 3D-gradient T1-weighted magnetic resonance scan of the shoulder was performed. The location of the injected fluid was independently assessed by 2 radiologists who were blinded as to the injection technique used. RESULTS: The accuracy of blind and US-guided injection was the same. The fluid was injected into the bursa in all cases. INTERPRETATION: Blind injection into the SSB is as reliable as US-guided injection and could therefore be used in daily routine. US-guided injections may offer a useful alternative in difficult cases, such as with changed anatomy postoperatively or when there is no effective clinical outcome.

Ultrasound of the rotator cuff with MRI and anatomic correlation.

Magnetic resonance imaging and high-resolution ultrasound (US) are frequently used for the detection of rotator cuff tears. The diagnostic yield of US is influenced by several factors as technique, knowledge of the imaging characteristics of anatomic and pathologic findings and of pitfalls. The purpose of this article is to illustrates that the standardized high-resolution US examination of the shoulder covers the entire rotator cuff and correlates with MR imaging and anatomic sections.