ABSTRACT
Prostate cancer remains a prevalent health concern, emphasizing the critical need for early diagnosis and precise treatment strategies to mitigate mortality rates. The accurate prediction of cancer grade is paramount for timely interventions. This paper introduces an approach to prostate cancer grading, framing it as a classification problem. Leveraging ResNet models on multi-scale patch-level digital pathology and the Diagset dataset, the proposed method demonstrates notable success, achieving an accuracy of 0.999 in identifying clinically significant prostate cancer. The study contributes to the evolving landscape of cancer diagnostics, offering a promising avenue for improved grading accuracy and, consequently, more effective treatment planning. By integrating innovative deep learning techniques with comprehensive datasets, our approach represents a step forward in the pursuit of personalized and targeted cancer care.
ABSTRACT
Cancer diagnosis and classification are pivotal for effective patient management and treatment planning. In this study, a comprehensive approach is presented utilizing ensemble deep learning techniques to analyze breast cancer histopathology images. Our datasets were based on two widely employed datasets from different centers for two different tasks: BACH and BreakHis. Within the BACH dataset, a proposed ensemble strategy was employed, incorporating VGG16 and ResNet50 architectures to achieve precise classification of breast cancer histopathology images. Introducing a novel image patching technique to preprocess a high-resolution image facilitated a focused analysis of localized regions of interest. The annotated BACH dataset encompassed 400 WSIs across four distinct classes: Normal, Benign, In Situ Carcinoma, and Invasive Carcinoma. In addition, the proposed ensemble was used on the BreakHis dataset, utilizing VGG16, ResNet34, and ResNet50 models to classify microscopic images into eight distinct categories (four benign and four malignant). For both datasets, a five-fold cross-validation approach was employed for rigorous training and testing. Preliminary experimental results indicated a patch classification accuracy of 95.31% (for the BACH dataset) and WSI image classification accuracy of 98.43% (BreakHis). This research significantly contributes to ongoing endeavors in harnessing artificial intelligence to advance breast cancer diagnosis, potentially fostering improved patient outcomes and alleviating healthcare burdens.
ABSTRACT
Prostate cancer remains a significant cause of male cancer mortality in the United States, with an estimated 288,300 new cases in 2023. Accurate grading of prostate cancer is crucial for ascertaining disease severity and shaping treatment strategies. Modern deep learning techniques show promise in grading biopsies, but there is a gap in integrating these advances into clinical practice. Our web platform tackles this challenge by integrating human expertise with AI-driven grading, incorporating diverse data sources. We gathered feedback from four pathologists and one medical practitioner to assess usability and real-world alignment through a survey and the NASA TLX Usability Test. Notably, 60% of users found it easy to navigate, rating it 5.5 out of 7 for ease of understanding. Users appreciated self-explanatory information in popup tabs. For ease of use, all users favored the detailed summary tab, rating it 6.5 out of 7. While 80% felt patient demographics beyond age were unnecessary, high-resolution biopsy images were deemed vital. Acceptability was high, with all users willing to adopt the app, and some believed it could reduce workload. The NASA TLX Usability Test indicated a low-moderate perceived workload, suggesting room for improved explanations and data visualization.
ABSTRACT
We present a case of a 72-year-old male with a history of a late 1980s metal-on-polyethylene total hip arthroplasty who presented with unilateral leg vascular compromise, joint pain, and stiffness and subsequently underwent revision for adverse local tissue reaction secondary to mechanically assisted crevice corrosion. His stable and extensively porous coated femoral implant had a legacy taper with no currently manufactured option for a non-Co-alloy femoral head. After shared decision-making with the patient, we opted to use an oxidized zirconium femoral head from another manufacturer with a similar taper during his revision surgery and documented that his vascular compromise resolved and his serum Co was undetectable 3 years after the revision.
ABSTRACT
BACKGROUND: Tailor's bunion, or bunionette, deformity is a common condition of the lateral forefoot. To aid in assessing the deformity, radiographic angular measurements are frequently used. The objective of this study was to determine the reliability and reproducibility of these angular measurements. METHODS: Thirty unique weightbearing dorsoplantar digital radiographs of pathologic feet were compiled. For these 30 radiographs and for ten repeated radiographs, six practicing clinicians measured the following angles: the fourth to fifth intermetatarsal angle, the lateral deviation angle, and the fifth metatarsophalangeal angle. Both traditional and modified versions of the fourth to fifth intermetatarsal angle were included. RESULTS: Intraclass correlation coefficient values were calculated for each of the angles studied. Intrarater reliability was highest for the fifth metatarsophalangeal angle and lowest for the lateral deviation angle. Intrarater reliability was higher for the traditional fourth to fifth intermetatarsal angle than for the modified version. The interrater reliability calculations revealed parallel findings. CONCLUSIONS: Accurate assessment is critical when planning for surgical intervention. Awareness of the relative reliability of these radiographic angular measurements can aid in preoperative planning and may be of benefit in procedure selection.
Subject(s)
Bunion, Tailor's/diagnostic imaging , Metatarsal Bones/diagnostic imaging , Humans , Metatarsal Bones/pathology , Observer Variation , Reproducibility of ResultsABSTRACT
Molecular profiling of urothelial cancers for therapeutic and prognostic potential has been very limited due to the absence of cancer-specific targeted therapies. We describe here 2 clinical cases with a histological diagnosis of an invasive sarcomatoid and a poorly differentiated carcinoma favoring urothelial with some neuroendocrine differentiation, two of the rarer types of urothelial cancers, which were evaluated for mutations in 212 genes for single-nucleotide variants and copy-number variants and 53 genes for fusions associated with solid tumors. In both cases, we identified variants in 2 genes, ARID1A and CDKN2A, indicative of the role of dysregulation of chromatin remodeling and cell cycle control as being common features of bladder cancer, consistent with the proposed model of tumorigenesis in these rare, highly aggressive pathological subtypes. The presence of a KRAS mutation in the poorly differentiated cancer and a TP53 mutation in the sarcomatoid tumor is indicative of a distinctive profile and adds a potential layer of molecular stratification to these rarer histological subtypes. We present a comparative analysis of the histological, clinical, and molecular profile of both cases and discuss the potential to delineate these tumors at the molecular level keeping in mind the possible therapeutic implications.
ABSTRACT
BACKGROUND: The normal radiographic anatomy of the foot and ankle, aside from my previous work, has been addressed only superficially or sparingly in the medical literature. This project correlates the detailed radiographic anatomy of the entire adult foot and ankle (two-dimensional) to osteology (three-dimensional). METHODS: Each bone's position was determined after meticulous examination and correlation to an articulated skeleton relative to the image receptor and direction of the x-ray beam, with correlation to the radiograph for confirmation. RESULTS: Images of each foot and distal leg bone ("front" and "back" perspectives) are presented alongside a corresponding radiographic image for comparison. The normal gross and radiographic anatomy is correlated and described for each radiographic positioning technique. CONCLUSIONS: Foundational knowledge is provided that future researchers can use as a baseline ("normal") and that students and practitioners can use for comparison when interpreting radiographs and distinguishing abnormal findings. The results of the original project, owing to its broad scope, have been divided into five parts: the lower leg, the greater tarsus, the lesser tarsus, the metatarsals, and the phalanges (the focus of this article).
Subject(s)
Anatomy, Regional/methods , Foot/diagnostic imaging , Imaging, Three-Dimensional/methods , Ankle/diagnostic imaging , Humans , Radiography , Toe Phalanges/diagnostic imagingABSTRACT
BACKGROUND: The normal radiographic anatomy of the foot and ankle, aside from my previous work, has been addressed only superficially or sparingly in the medical literature. This project correlates the detailed radiographic anatomy of the entire adult foot and ankle (two-dimensional) to osteology (three-dimensional). METHODS: Each bone's position was determined after meticulous examination and correlation to an articulated skeleton relative to the image receptor and direction of the x-ray beam, with correlation to the radiograph for confirmation. RESULTS: Images of each foot and distal leg bone ("front" and "back" perspectives) are presented alongside a corresponding radiographic image for comparison. The normal gross and radiographic anatomy is correlated and described for each radiographic positioning technique. CONCLUSIONS: Foundational knowledge is provided that future researchers can use as a baseline ("normal") and that students and practitioners can use for comparison when interpreting radiographs and distinguishing abnormal findings. The results of the original project, owing to its broad scope, have been divided into five parts: the lower leg, the greater tarsus, the lesser tarsus, the metatarsals (the focus of this article), and the phalanges.
Subject(s)
Anatomy, Regional , Ankle Joint/diagnostic imaging , Metatarsal Bones/diagnostic imaging , Adult , HumansABSTRACT
BACKGROUND: The normal radiographic anatomy of the foot and ankle, aside from my previous work, has been addressed only superficially or sparingly in the medical literature. This project correlates the detailed radiographic anatomy of the entire adult foot and ankle (two-dimensional) to osteology (three-dimensional). METHODS: Each bone's position was determined after meticulous examination and correlation to an articulated skeleton relative to the image receptor and direction of the x-ray beam, with correlation to the radiograph for confirmation. RESULTS: Images of each foot and distal leg bone ("front" and "back" perspectives) are presented alongside a corresponding radiographic image for comparison. The normal gross and radiographic anatomy is correlated and described for each radiographic positioning technique. CONCLUSIONS: Foundational knowledge is provided that future researchers can use as a baseline ("normal") and that students and practitioners can use for comparison when interpreting radiographs and distinguishing abnormal findings. The results of the original project, owing to its broad scope, have been divided into five parts: the lower leg, the greater tarsus, the lesser tarsus (the focus of this article), the metatarsals, and the phalanges.
Subject(s)
Ankle/diagnostic imaging , Tarsal Bones/diagnostic imaging , HumansABSTRACT
BACKGROUND: Normal radiographic anatomy of the foot and ankle, aside from my previous work, has been addressed only superficially or sparingly in the medical literature. This project correlates detailed radiographic anatomy of the entire adult foot and ankle (two-dimensional) to osteology (three-dimensional). METHODS: Each bone's position was determined after meticulous examination and correlation to an articulated skeleton relative to the image receptor and direction of the x-ray beam, with correlation to the radiograph for confirmation. RESULTS: Images of each foot and distal leg bone ("front" and "back" perspectives) are presented alongside a corresponding radiographic image for comparison. The normal gross and radiographic anatomy is correlated and described for each radiographic positioning technique. CONCLUSIONS: Foundational knowledge is provided that future researchers can use as a baseline ("normal") and that students and practitioners can use for comparison when interpreting radiographs and distinguishing abnormal findings. The results of the original project, owing to its broad scope, have been divided into five parts: the lower leg, the greater tarsus (the focus of this article), the lesser tarsus, the metatarsals, and the phalanges.
Subject(s)
Calcaneus/anatomy & histology , Calcaneus/diagnostic imaging , Talus/anatomy & histology , Talus/diagnostic imaging , Adult , Ankle/anatomy & histology , Ankle/diagnostic imaging , Foot/anatomy & histology , Foot/diagnostic imaging , Humans , Imaging, Three-DimensionalABSTRACT
The normal radiographic anatomy of the foot and ankle, aside from my previous work, has been addressed only superficially or sparingly in the medical literature. This project correlates the detailed radiographic anatomy of the entire adult foot and ankle (two-dimensional) to osteology (three-dimensional). Each bone's position was determined after meticulous examination and correlation to an articulated skeleton relative to the image receptor and direction of the x-ray beam, with correlation to the radiograph for confirmation. Images of each foot and distal leg bone ("front" and "back" perspectives) are presented alongside a corresponding radiographic image for comparison. The normal gross and radiographic anatomy is correlated and described for each radiographic positioning technique. Foundational knowledge is provided that future researchers can use as a baseline ("normal") and that students and practitioners can use for comparison when interpreting radiographs and distinguishing abnormal findings. The findings from the original project, owing to its broad scope, have been divided into five parts: the lower leg (the focus of this paper), the greater tarsus, the lesser tarsus, the metatarsals, and the phalanges.
Subject(s)
Fibula/diagnostic imaging , Foot Bones/diagnostic imaging , Tibia/diagnostic imaging , Fibula/anatomy & histology , Foot Bones/anatomy & histology , Humans , Imaging, Three-Dimensional , Tibia/anatomy & histologyABSTRACT
Abstract BACKGROUND: Normal radiographic anatomy of the foot and ankle, aside from this author's previous work, has only been addressed superficially or sparingly in the medical literature. This project correlates detailed radiographic anatomy of the entire adult foot and ankle (two-dimensional) to osteology (three-dimensional). METHODS: Each bone's position was determined after meticulous examination and correlation to an articulated skeleton relative to the image receptor and direction of the x-ray beam, with correlation to the radiograph for confirmation. RESULTS: Images of each foot and distal leg bone ("front" and "back" perspectives) are presented alongside a corresponding radiographic image for comparison. The normal gross and radiographic anatomy is correlated and described for each radiographic positioning technique. CONCLUSIONS: Foundational knowledge is provided that (1) future researchers can use as a baseline ("normal"), and (2) both students and practitioners can use for comparison when interpreting radiographs and distinguishing abnormal findings.
ABSTRACT
A 45-year-old man was seen in consultation for evaluation of a spiculated right-lower-lobe mass that enlarged over 1 year. The patient had suffered accidental instillation of activated charcoal into the right lung via nasogastric tube 2 years prior to this consultation, with resultant respiratory failure, pneumonia, and pneumothorax. Biopsy of the mass showed anthracosis and granulomatous inflammation. A positron emission tomogram was strongly positive at the lesion, and right-lower-lobectomy with partial diaphragmatic resection was performed. On gross examination of the mass, a charcoal concretion was evident. Histologic examination showed intrinsic and surrounding granulomatous inflammation, but without tumor. The patient recovered uneventfully, and after 1 year had not experienced further complications.
Subject(s)
Charcoal/administration & dosage , Lung/physiopathology , Respiratory Aspiration , Anthracosilicosis , Charcoal/adverse effects , Humans , Maine , Male , Middle Aged , Treatment OutcomeABSTRACT
Detailed radiographic anatomy of the entire talus bone has not been previously described in the literature. We used radiopaque wire markers to identify 17 articular and nonarticular anatomical landmarks of the talus. Standard radiographic views of the foot and ankle were obtained: lateral (foot and ankle); anteroposterior, mortise, medial oblique, and lateral oblique (ankle); and dorsoplantar, medial oblique, and lateral oblique (foot). The resultant two-dimensional images are correlated to the three-dimensional anatomical specimen, and normal radiographic anatomy is described. Additionally, useful radiographic views for each anatomical landmark are identified. Composite figures of each useful view are presented as a pictorial atlas.
Subject(s)
Awards and Prizes , Podiatry , Talus/anatomy & histology , Talus/diagnostic imaging , Humans , Radiography/methods , Reference Values , United StatesABSTRACT
We report a very rare case of a lumbar nerve root schwannoma presenting with torsion and infarction. The patient was a 16-year-old male presenting with severe low back pain and urinary retention following an aggressive game of hockey. Subsequent MRI of the lumbar spine revealed a nonenhancing lumbar intradural lesion at the level of L3. The patient was taken to the operating room where he underwent a bilateral L2 and L3 laminectomy and gross total resection of an intradural nerve root tumor, which appeared to have undergone torsion and infarction. Subsequent histopathological examination of the surgical specimen verified the diagnosis of infarcted schwannoma. This is a unique case of lumbar nerve root schwannoma, with atypical MRI findings, presenting with infarction due to torsion of the involved nerve root.
Subject(s)
Nerve Sheath Neoplasms/pathology , Neurilemmoma/pathology , Spinal Neoplasms/pathology , Spinal Nerve Roots/pathology , Adolescent , Humans , Lumbosacral Region , Magnetic Resonance Imaging , Male , Nerve Sheath Neoplasms/surgery , Neurilemmoma/surgery , Spinal Neoplasms/surgery , Spinal Nerve Roots/surgery , Torsion AbnormalityABSTRACT
The purpose of this study was to determine the histologic class and immunologic phenotype of lymphomas presenting initially in the oral cavity and whether this correlated to a high incidence of Epstein-Barr virus (EBV) infection as has been reported with lymphomas in the nasal cavity. Seventy-one cases of oral lymphomas from the oral pathology referral service were analyzed retrospectively. They were classified according to the Revised European American Lymphoma (REAL) classification system using routine immunohistochemistry. EBV infection was determined by detection of early viral RNA sequences (EBER) and latent membrane protein (LMP-1) expression. Only non-Hodgkin's lymphomas were observed, with a female predominance of 2:1. They were primarily of B-cell origin and histologically classified mainly as large B-cell type (68%); T-cell lymphomas were rare (8%). EBV infection was observed in 14% of the B-cell lymphomas, an incidence rate higher than that reported in studies of B-cell lymphomas not located in the oral cavity but not as high as that observed in pleomorphic T-cell lymphomas (all sites, 36%) or nasal cavity T-cell lymphomas (nearly 100%). Interestingly, EBV proliferation did not correlate with expression of either Bcl-2 or p53.