Deep Learning Diagnosis and Classification of Rotator Cuff Tears on Shoulder MRI.

BACKGROUND: Detection of rotator cuff tears, a common cause of shoulder disability, can be time-consuming and subject to reader variability. Deep learning (DL) has the potential to increase radiologist accuracy and consistency. PURPOSE: The aim of this study was to develop a prototype DL model for detection and classification of rotator cuff tears on shoulder magnetic resonance imaging into no tear, partial-thickness tear, or full-thickness tear. MATERIALS AND METHODS: This Health Insurance Portability and Accountability Act-compliant, institutional review board-approved study included a total of 11,925 noncontrast shoulder magnetic resonance imaging scans from 2 institutions, with 11,405 for development and 520 dedicated for final testing. A DL ensemble algorithm was developed that used 4 series as input from each examination: fluid-sensitive sequences in 3 planes and a sagittal oblique T1-weighted sequence. Radiology reports served as ground truth for training with categories of no tear, partial tear, or full-thickness tear. A multireader study was conducted for the test set ground truth, which was determined by the majority vote of 3 readers per case. The ensemble comprised 4 parallel 3D ResNet50 convolutional neural network architectures trained via transfer learning and then adapted to the targeted domain. The final tear-type prediction was determined as the class with the highest probability, after averaging the class probabilities of the 4 individual models. RESULTS: The AUC overall for supraspinatus, infraspinatus, and subscapularis tendon tears was 0.93, 0.89, and 0.90, respectively. The model performed best for full-thickness supraspinatus, infraspinatus, and subscapularis tears with AUCs of 0.98, 0.99, and 0.95, respectively. Multisequence input demonstrated higher AUCs than single-sequence input for infraspinatus and subscapularis tendon tears, whereas coronal oblique fluid-sensitive and multisequence input showed similar AUCs for supraspinatus tendon tears. Model accuracy for tear types and overall accuracy were similar to that of the clinical readers. CONCLUSIONS: Deep learning diagnosis of rotator cuff tears is feasible with excellent diagnostic performance, particularly for full-thickness tears, with model accuracy similar to subspecialty-trained musculoskeletal radiologists.

Deep Learning Reconstruction Enables Prospectively Accelerated Clinical Knee MRI.

Background MRI is a powerful diagnostic tool with a long acquisition time. Recently, deep learning (DL) methods have provided accelerated high-quality image reconstructions from undersampled data, but it is unclear if DL image reconstruction can be reliably translated to everyday clinical practice. Purpose To determine the diagnostic equivalence of prospectively accelerated DL-reconstructed knee MRI compared with conventional accelerated MRI for evaluating internal derangement of the knee in a clinical setting. Materials and Methods A DL reconstruction model was trained with images from 298 clinical 3-T knee examinations. In a prospective analysis, patients clinically referred for knee MRI underwent a conventional accelerated knee MRI protocol at 3 T followed by an accelerated DL protocol between January 2020 and February 2021. The equivalence of the DL reconstruction of the images relative to the conventional images for the detection of an abnormality was assessed in terms of interchangeability. Each examination was reviewed by six musculoskeletal radiologists. Analyses pertaining to the detection of meniscal or ligament tears and bone marrow or cartilage abnormalities were based on four-point ordinal scores for the likelihood of an abnormality. Additionally, the protocols were compared with use of four-point ordinal scores for each aspect of image quality: overall image quality, presence of artifacts, sharpness, and signal-to-noise ratio. Results A total of 170 participants (mean age ± SD, 45 years ± 16; 76 men) were evaluated. The DL-reconstructed images were determined to be of diagnostic equivalence with the conventional images for detection of abnormalities. The overall image quality score, averaged over six readers, was significantly better (P < .001) for the DL than for the conventional images. Conclusion In a clinical setting, deep learning reconstruction enabled a nearly twofold reduction in scan time for a knee MRI and was diagnostically equivalent with the conventional protocol. © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Roemer in this issue.

Follicular psoriasis: a report of 5 cases and review of the literature, likely an under-recognized yet distinctive variant of psoriasis.

Psoriasis is a common autoimmune dermatosis representing an interplay between certain genetic predisposing factors along with clonally restricted Th1 T cells responding to epidermal keratinocyte derived antigen. A unique IL17/IL23 cytokine-rich milieu is pathogenetically significant and conducive to its salient histomorphologic features, such as epidermal hyperplasia and intraepidermal influx of neutrophils. The classic cutaneous manifestation is that of plaque psoriasis also referred to as psoriasis vulgaris with characteristic well-circumscribed erythematous plaques covered by silvery scales. Follicular psoriasis is an uncommon variant manifesting as a scaly folliculocentric hyperkeratotic eruption of the trunk and extremities, irrespective of the presence or absence of conventional lesions of psoriasis vulgaris. In this study we present 5 cases of follicular psoriasis, review the literature, and provide a proposal regarding relevant pathologic findings and potential pathogenetic mechanisms. The incidence of follicular psoriasis is unknown, emphasizing its rarity given the overall incidence of conventional psoriasis in the general population. Owing to the lack of awareness, this clinical presentation is often mistaken for other follicular dermatoses, including bacterial folliculitis, pityriasis rubra pilaris, keratosis pilaris, or follicular eczema.

Using Deep Learning to Accelerate Knee MRI at 3 T: Results of an Interchangeability Study.

OBJECTIVE. Deep learning (DL) image reconstruction has the potential to disrupt the current state of MRI by significantly decreasing the time required for MRI examinations. Our goal was to use DL to accelerate MRI to allow a 5-minute comprehensive examination of the knee without compromising image quality or diagnostic accuracy. MATERIALS AND METHODS. A DL model for image reconstruction using a variational network was optimized. The model was trained using dedicated multisequence training, in which a single reconstruction model was trained with data from multiple sequences with different contrast and orientations. After training, data from 108 patients were retrospectively undersampled in a manner that would correspond with a net 3.49-fold acceleration of fully sampled data acquisition and a 1.88-fold acceleration compared with our standard twofold accelerated parallel acquisition. An interchangeability study was performed, in which the ability of six readers to detect internal derangement of the knee was compared for clinical and DL-accelerated images. RESULTS. We found a high degree of interchangeability between standard and DL-accelerated images. In particular, results showed that interchanging the sequences would produce discordant clinical opinions no more than 4% of the time for any feature evaluated. Moreover, the accelerated sequence was judged by all six readers to have better quality than the clinical sequence. CONCLUSION. An optimized DL model allowed acceleration of knee images that performed interchangeably with standard images for detection of internal derangement of the knee. Importantly, readers preferred the quality of accelerated images to that of standard clinical images.

Reexcision Perineural Invasion and Epithelial Sheath Neuroma Possibly on a Spectrum of Postinjury Reactive Hyperplasia Mediated by IL-6.

Epithelial sheath neuroma is a rarely recognized but established entity in the medical literature. First described in 2000 by Requena et al, there have only been 7 published cases to date, mostly in female patients and presenting as symptomatic solitary lesions on the back without a known history of trauma. In 2006, Beer et al described and reviewed a dozen cases in which epithelial sheath neuroma-like features were seen in the advent of a surgical procedure, which was termed "re-excision perineural invasion" and attributed to possible eccrine duct implantation during surgery. Our case is a 66-year-old male patient who underwent an excision of a melanocytic neoplasm in which a reactive epithelial sheath neuroma was incidentally discovered in the excision specimen, adjacent to the biopsy site cicatrix. Histologically, there was benign cutaneous nerve hyperplasia with a proliferation of squamous epithelium in intimate apposition to the nerve bundles in the superficial dermis. We postulate that the process active in the formation of re-excision perineural invasion is the same as in epithelial sheath neuroma and that minor trauma not appreciable on histologic examination is responsible in the latter entity. We performed IL-6 staining and documented that IL-6 was upregulated at the interface of the nerve and reactive epithelium, but was absent in nerves distant from the site of surgery, suggesting that IL-6 may be essential to the lesion's development. The recognition of reactive epithelial sheath neuroma including the subcategory of re-excision perineural invasion is crucial for the dermatopathologist to prevent mislabeling this reactive entity as a perineural squamous cell carcinoma, which has clinical consequences for the patient such as wider re-excision and radiation treatment. Additionally, we have identified a potential pathophysiologic basis for this lesion.

De novo intraepidermal epithelioid melanocytic dysplasia: an emerging entity.

De novo intraepidermal epithelioid melanocytic dysplasia represents a distinctive form of intraepidermal melanocytic dysplasia. Although these lesions are atypical, they are not diagnostic of melanoma. They are considered a part of the atypical mole phenotype and may define a point in the natural course of melanomagenesis.

MRI evaluation of costal cartilage injuries.

OBJECTIVE: The usefulness of MRI in costal cartilage injuries has not been shown. We report the MRI findings in a series of patients with costal cartilage injuries. CONCLUSION: MRI can be a useful technique in the diagnosis of costal cartilage injuries.

Bare area of the glenoid: magnetic resonance appearance with arthroscopic correlation.

OBJECTIVE: To review the radiologic findings of a rarely reported focal area of acquired cartilage thinning located at the center of the glenoid fossa. METHODS: We retrospectively reviewed the medical records of 3 patients, each possessing a bare area of the glenoid detected on magnetic resonance (MR) imaging. A literature search was performed to obtain the most current information regarding this uncommon entity. RESULTS: Magnetic resonance imaging of the glenoid demonstrated a smoothly marginated subcentimeter area of thinning of the central articular cartilage containing hyperintense joint fluid or contrast in the case with MR arthrography. Arthroscopic correlation was obtained in a single case. CONCLUSIONS: The bare area of the glenoid is an acquired cartilage defect located at the center of the glenoid articular surface. Characteristic findings can be seen on MR imaging. Care should be taken not to mistake this acquired condition for posttraumatic defects of the glenoid articular cartilage.