Utility of deep learning for the diagnosis of otosclerosis on temporal bone CT.

OBJECTIVE: Diagnosis of otosclerosis on temporal bone CT images is often difficult because the imaging findings are frequently subtle. Our aim was to assess the utility of deep learning analysis in diagnosing otosclerosis on temporal bone CT images. METHODS: A total of 198 temporal bone CT images were divided into the training set (n = 140) and the test set (n = 58). The final diagnosis (otosclerosis-positive or otosclerosis-negative) was determined by an experienced senior radiologist who carefully reviewed all 198 temporal bone CT images while correlating with clinical and intraoperative findings. In deep learning analysis, a rectangular target region that includes the area of the fissula ante fenestram was extracted and fed into the deep learning training sessions to create a diagnostic model. Transfer learning was used with the deep learning model architectures of AlexNet, VGGNet, GoogLeNet, and ResNet. The test data set was subsequently analyzed using these models and by another radiologist with 3 years of experience in neuroradiology following completion of a neuroradiology fellowship. The performance of the radiologist and the deep learning models was determined using the senior radiologist's diagnosis as the gold standard. RESULTS: The diagnostic accuracies were 0.89, 0.72, 0.81, 0.86, and 0.86 for the subspecialty trained radiologist, AlexNet, VGGNet, GoogLeNet, and ResNet, respectively. The performances of VGGNet, GoogLeNet, and ResNet were not significantly different compared to the radiologist. In addition, GoogLeNet and ResNet demonstrated non-inferiority compared to the radiologist. CONCLUSIONS: Deep learning technique may be a useful supportive tool in diagnosing otosclerosis on temporal bone CT. KEY POINTS: • Deep learning can be a helpful tool for the diagnosis of otosclerosis on temporal bone CT. • Deep learning analyses with GoogLeNet and ResNet demonstrate non-inferiority when compared to the subspecialty trained radiologist. • Deep learning may be particularly useful in medical institutions without experienced radiologists.

Notification System for Overdue Radiology Recommendations Improves Rates of Follow-Up and Diagnosis.

OBJECTIVE. The purpose of this study was to quantify improved rates of follow-up and additional important diagnoses made after notification for overdue workups recommended by radiologists. MATERIALS AND METHODS. Standard reports from imaging studies performed at our institution from October through November 2016 were searched for the words "recommend" or "advised," yielding 9784 studies. Of these, 5245 were excluded, yielding 4539 studies; reports for 1599 of these 4539 consecutive studies were reviewed to identify firm or soft recommendations or findings requiring immediate management. If recommended follow-ups were incomplete within 1 month of the advised time, providers were notified. Compliance was calculated before and after notification and was compared using a one-sample test of proportion. RESULTS. Of 1599 patients, 92 were excluded because they had findings requiring immediate management, and 684 were excluded because of soft recommendations, yielding 823 patients. Of these patients, 125 were not yet overdue for follow-up and were excluded, and 18 were excluded because of death or transfer to another institution. Of the remaining 680 patients, follow-up was completed for 503 (74.0%). A total of 177 (26.0%) of the 680 patients were overdue for follow-up, and providers were notified. Of these 177 patients, 36 (20.3%) completed their follow-ups after notification, 34 (19.2%) had follow-up designated by the provider as nonindicated, and 107 (60.5%) were lost to follow-up, yielding four clinically important diagnoses: one biopsy-proven malignancy, one growing mass, and two thyroid nodules requiring biopsy. The rate of incomplete follow-ups after communication decreased from 26.0% (177/680) to 20.7% (141/680) (95% CI, 17.7-23.9%; p = .002), with a 20.4% reduction in relative risk of noncompliance, and 39.5% (70/177) of overdue cases were resolved when nonindicated studies were included. CONCLUSION. Notification of overdue imaging recommendations reduces incomplete follow-ups and yields clinically important diagnoses.

Cystic cervical lymph nodes of papillary thyroid carcinoma, tuberculosis and human papillomavirus positive oropharyngeal squamous cell carcinoma: utility of deep learning in their differentiation on CT.

OBJECTIVES: Cervical lymph nodes with internal cystic changes are seen with several pathologies, including papillary thyroid carcinoma (PTC), tuberculosis (TB), and HPV-positive oropharyngeal squamous cell carcinoma (HPV+OPSCC). Differentiating these lymph nodes is difficult in the absence of a known primary tumor or reliable medical history. In this study, we assessed the utility of deep learning in differentiating the pathologic lymph nodes of PTC, TB, and HPV+OPSCC on CT. METHODS: A total of 173 lymph nodes (55 PTC, 58 TB, and 60 HPV+OPSCC) were selected based on pathology records and suspicious morphological features. These lymph nodes were divided into the training set (n = 131) and the test set (n = 42). In deep learning analysis, JPEG lymph node images were extracted from the CT slice that included the largest area of each node and fed into a deep learning training session to create a diagnostic model. Transfer learning was used with the deep learning model architecture of ResNet-101. Using the test set, the diagnostic performance of the deep learning model was compared against the histopathological diagnosis and to the diagnostic performances of two board-certified neuroradiologists. RESULTS: Diagnostic accuracy of the deep learning model was 0.76 (=32/42), whereas those of Radiologist 1 and Radiologist 2 were 0.48 (=20/42) and 0.41 (=17/42), respectively. Deep learning derived diagnostic accuracy was significantly higher than both of the two neuroradiologists (P < 0.01, respectively). CONCLUSION: Deep learning algorithm holds promise to become a useful diagnostic support tool in interpreting cervical lymphadenopathy.

Role of cervical spine MRI in the setting of negative cervical spine CT in blunt trauma: Critical additional information in the setting of clinical findings suggestive of occult injury.

BACKGROUND AND PURPOSE: Cervical spine injury is common in the setting of blunt trauma and there is consensus that cervical spine CT (CSCT) is the image modality of choice for initial evaluation for blunt trauma related injuries of the cervical spine. However, there is disagreement in the literature with regards to further evaluation of blunt trauma patients with cervical spine MRI (CSMRI) after negative CSCT when there is persistent clinical concern for occult trauma related injury. The purpose of this study is to examine the utility of CSMRI for detection of occult injury in blunt trauma patients after negative CSCT. MATERIALS AND METHODS: We reviewed records for 7,301 patients admitted for blunt trauma (November 2007-December 2013) and identified 259 who underwent CSMRI after a negative CSCT. These CSMRIs were reviewed to determine the number and type of significant CT occult injuries identified and clinical indications that led to CSMRI acquisition. RESULTS AND CONCLUSIONS: CSMRI detected significant injuries following negative CSCT in 31% (81/259) of patients. There were 15 cord contusions/infarcts, 9 bone contusions/fractures, 7 spinal canal hemorrhages and 66 soft tissue injuries. Upper extremity neurological deficit had greatest positive predictive value (PPV) for detection of CT-occult injury on CSMRI of 43% (23/53), followed by equivocal CSCT findings (38%, 18/47), presence of extra-cervical injuries (34%, 20/58), midline cervical tenderness (20%, 17/85), and isolated lower extremity neurological deficit (0%, 0/16). CSMRI is recommended following negative CSCT in the evaluation of blunt cervical spine trauma when appropriate clinical concerns are present.

Determining the optimal osteotomy distance with the fibula free flap in mandibular reconstruction.

OBJECTIVE: Fibula free tissue transfer is a common and reliable method for mandibular reconstruction. Functional outcomes from this procedure are dependent on the successful union of the osseous segments postoperatively. This study was conducted to define the maximum gap-size criteria for osseous union to occur at osteotomy sites in fibula free flap reconstruction of the mandible. STUDY DESIGN: Retrospective chart review. SETTING: Tertiary care academic center. SUBJECTS AND METHODS: A retrospective chart review of computed tomography and medical records was conducted on patients who underwent fibula free flap surgery and had imaging of the mandible at <3 months and >6 months after surgery. Distances between osteotomies were measured and evaluated for interval healing. Secondary data included subject age, sex, smoking status, diabetes, number of osteotomies, complications, and adjuvant therapy. RESULTS: Thirty-eight osteotomy sites were analyzed from thirteen subjects and a total of 190 measurements were made. The mean gap size at the first scan that demonstrated union by the second scan interval was 1.31 mm and mean gap size demonstrating non-union was 2.55 mm (p < 0.01). Complication rate, number of osetotomies, adjuvant therapy, or medical co-morbidities did not significantly affect rates of union. CONCLUSIONS: In this study, osseous union was achieved with a mean osteotomy gap size of 1.31 mm. The data suggests that distances between ossesous segments >2 .55mm have a higher risk of non-union. We believe the information from this study will help augment current and future techniques in the field of mandible reconstruction.

A sodium-pump-mediated afterhyperpolarization in pyramidal neurons.

The sodium-potassium ATPase (i.e., the "sodium pump") plays a central role in maintaining ionic homeostasis in all cells. Although the sodium pump is intrinsically electrogenic and responsive to dynamic changes in intracellular sodium concentration, its role in regulating neuronal excitability remains unclear. Here we describe a physiological role for the sodium pump in regulating the excitability of mouse neocortical layer 5 and hippocampal CA1 pyramidal neurons. Trains of action potentials produced long-lasting (∼20 s) afterhyperpolarizations (AHPs) that were insensitive to blockade of voltage-gated calcium channels or chelation of intracellular calcium, but were blocked by tetrodotoxin, ouabain, or the removal of extracellular potassium. Correspondingly, the AHP time course was similar to the decay of activity-induced increases in intracellular sodium, whereas intracellular calcium decayed at much faster rates. To determine whether physiological patterns of activity engage the sodium pump, we replayed in vitro a place-specific burst of 15 action potentials recorded originally in vivo in a CA1 "place cell" as the animal traversed the associated place field. In both layer 5 and CA1 pyramidal neurons, this "place cell train" generated small, long-lasting AHPs capable of reducing neuronal excitability for many seconds. Place-cell-train-induced AHPs were blocked by ouabain or removal of extracellular potassium, but not by intracellular calcium chelation. Finally, we found calcium contributions to the AHP to be temperature dependent: prominent at room temperature, but largely absent at 35°C. Our results demonstrate a previously unappreciated role for the sodium-potassium ATPase in regulating the excitability of neocortical and hippocampal pyramidal neurons.

Twig-like middle cerebral arteries: Clinical and radiological findings.

BACKGROUND AND PURPOSE: Aplastic or twig-like middle cerebral artery (MCA) is a rare vascular anomaly characterized by replacement of the M1 segment by a plexiform network of small vessels. Though rare, familiarity with this entity and ability to differentiate it from radiological mimics such as moyamoya changes and steno-occlusive diseases are important. We review the clinical and radiological manifestations of patients diagnosed with twig-like MCA on cerebral angiograms over a five-year period. MATERIALS AND METHODS: Retrospective review of all patients diagnosed with twig-like MCA on cerebral angiograms was performed from January 2015 to January 2020. This was the inclusion criterion for this retrospective study. For each patient, demographic data, clinical presentation, imaging findings and management strategies were reviewed. RESULTS AND CONCLUSIONS: Between January 2015 and January 2020, three patients with twig-like MCA were identified from 657 patients who underwent four-vessel diagnostic cerebral angiograms (0.45%). In all three cases, the involvement was unilateral (two left-sided and one right- sided). Two patients were male, and one was female. Patients ages were 25, 26 and 46 years. Two of the three patients presented with headache and the third patient with pulsatile tinnitus. There were otherwise no ischemic or hemorrhagic changes. No other vascular anomaly was identified. Twig-like MCA is a rare anatomical variant in which a plexiform network of small vessels replaces the M1 segment of the MCA. Accurate diagnosis and distinguishing this entity from radiological mimics such as moyamoya and steno-occlusive diseases are important for appropriate management and to prevent unnecessary investigations.

Cystic cervical lymph nodes of papillary thyroid carcinoma, tuberculosis and human papillomavirus positive oropharyngeal squamous cell carcinoma: Comparative CT analysis for their differentiation.

PURPOSE: Cervical lymph nodes with cystic changes are an important finding seen with several pathologies including papillary thyroid carcinoma (PTC), tuberculosis (TB) and HPV-positive oropharyngeal squamous cell carcinoma (HPV + OPSCC). In the absence of known primary tumor or conclusive medical history, differentiating among these nodes is difficult. We compared the pathologic nodes of PTC, TB and HPV + OPSCC to identify imaging features useful for their differentiation. MATERIALS AND METHODS: Fifty-five PTC, 58 TB and 51 HPV + OPSCC nodes were selected based on surgical pathology records and suspicious morphological features. These nodes were compared for morphological features: long axis length, nodal shape, nodal location, presence of cystic change, area of cystic change:area of entire node ratio, Hounsfield unit of the cystic component, degree of enhancement, enhancement pattern, presence of calcification, presence of perinodal infiltration, and presence of surrounding inflammatory changes. RESULTS: PTC nodes formed calcifications more frequently and demonstrated greater enhancement (P < 0.01). TB nodes were characterized by their irregular shape (P < 0.05), irregular enhancement surrounding the cystic change (P < 0.01), greater frequencies of perinodal infiltration (P < 0.01) and surrounding inflammatory changes (P < 0.01). While no unique features were seen with HPV+OPSCC, they were characterized by the absence of those features that distinguished the other groups: these nodes tended to have smooth, circumscribed margins with no hyperenhancement, calcifications or inflammatory changes. PTC and TB nodes were more frequently identified in the lower neck, while HPV+OPSCC nodes were localized to the upper neck (P < 0.01). CONCLUSIONS: PTC, TB and HPV + OPSCC lymph nodes can be differentiated based on their morphologies and locations.