Using Artificial Intelligence to Stratify Normal versus Abnormal Chest X-rays: External Validation of a Deep Learning Algorithm at East Kent Hospitals University NHS Foundation Trust.

Background: The chest radiograph (CXR) is the most frequently performed radiological examination worldwide. The increasing volume of CXRs performed in hospitals causes reporting backlogs and increased waiting times for patients, potentially compromising timely clinical intervention and patient safety. Implementing computer-aided detection (CAD) artificial intelligence (AI) algorithms capable of accurate and rapid CXR reporting could help address such limitations. A novel use for AI reporting is the classification of CXRs as 'abnormal' or 'normal'. This classification could help optimize resource allocation and aid radiologists in managing their time efficiently. Methods: qXR is a CE-marked computer-aided detection (CAD) software trained on over 4.4 million CXRs. In this retrospective cross-sectional pre-deployment study, we evaluated the performance of qXR in stratifying normal and abnormal CXRs. We analyzed 1040 CXRs from various referral sources, including general practices (GP), Accident and Emergency (A&E) departments, and inpatient (IP) and outpatient (OP) settings at East Kent Hospitals University NHS Foundation Trust. The ground truth for the CXRs was established by assessing the agreement between two senior radiologists. Results: The CAD software had a sensitivity of 99.7% and a specificity of 67.4%. The sub-group analysis showed no statistically significant difference in performance across healthcare settings, age, gender, and X-ray manufacturer. Conclusions: The study showed that qXR can accurately stratify CXRs as normal versus abnormal, potentially reducing reporting backlogs and resulting in early patient intervention, which may result in better patient outcomes.

Role of an Automated Deep Learning Algorithm for Reliable Screening of Abnormality in Chest Radiographs: A Prospective Multicenter Quality Improvement Study.

In medical practice, chest X-rays are the most ubiquitous diagnostic imaging tests. However, the current workload in extensive health care facilities and lack of well-trained radiologists is a significant challenge in the patient care pathway. Therefore, an accurate, reliable, and fast computer-aided diagnosis (CAD) system capable of detecting abnormalities in chest X-rays is crucial in improving the radiological workflow. In this prospective multicenter quality-improvement study, we have evaluated whether artificial intelligence (AI) can be used as a chest X-ray screening tool in real clinical settings. Methods: A team of radiologists used the AI-based chest X-ray screening tool (qXR) as a part of their daily reporting routine to report consecutive chest X-rays for this prospective multicentre study. This study took place in a large radiology network in India between June 2021 and March 2022. Results: A total of 65,604 chest X-rays were processed during the study period. The overall performance of AI achieved in detecting normal and abnormal chest X-rays was good. The high negatively predicted value (NPV) of 98.9% was achieved. The AI performance in terms of area under the curve (AUC), NPV for the corresponding subabnormalities obtained were blunted CP angle (0.97, 99.5%), hilar dysmorphism (0.86, 99.9%), cardiomegaly (0.96, 99.7%), reticulonodular pattern (0.91, 99.9%), rib fracture (0.98, 99.9%), scoliosis (0.98, 99.9%), atelectasis (0.96, 99.9%), calcification (0.96, 99.7%), consolidation (0.95, 99.6%), emphysema (0.96, 99.9%), fibrosis (0.95, 99.7%), nodule (0.91, 99.8%), opacity (0.92, 99.2%), pleural effusion (0.97, 99.7%), and pneumothorax (0.99, 99.9%). Additionally, the turnaround time (TAT) decreased by about 40.63% from pre-qXR period to post-qXR period. Conclusions: The AI-based chest X-ray solution (qXR) screened chest X-rays and assisted in ruling out normal patients with high confidence, thus allowing the radiologists to focus more on assessing pathology on abnormal chest X-rays and treatment pathways.

Gynecologic large cell neuroendocrine carcinoma: A review.

Large cell neuroendocrine carcinomas (LCNEC) are rare, aggressive high-grade neuroendocrine neoplasms within the neuroendocrine cell lineage spectrum. This manuscript provides a detailed review of published literature on LCNEC of gynecological origin. We performed a PubMed search for material available on gynecologic LCNEC. We analyzed 104 unique cases of gynecologic LCNECs, of which 45 were cervical primary, 45 were ovarian, 13 were uterine, and 1 was vaginal. A total of 45 cases of cervical LCNEC were identified with a median age of 36 years. Median overall survival was 16 months. We identified 45 ovarian LCNEC cases in the published literature with a median age of 54 years. Median overall survival was 8 months. 13 LCNEC cases of uterine origin were identified; 12 out of 13 were of endometrial origin and the median age was 71 years. The majority of patients presented with Stage III/IV disease (stages I-IV were 31%, 8%, 38%, and 23%, respectively). Gynecologic LCNEC is an aggressive malignancy. Our current understanding of the disease biology is very limited. Efforts are required to better understand the genomic and molecular characterizations of gynecological LCNEC. These efforts will elucidate the underlying oncogenic pathways and driver mutations as potential targets.

Post FDA approval analysis of 200 gallium-68 DOTATATE imaging: A retrospective analysis in neuroendocrine tumor patients.

Gallium-68 DOTATATE provides physiologic imaging and assists in disease localization for somatostatin receptor (SSTR) positive neuroendocrine tumor (NET) patients. However, questions regarding usefulness of gallium- 68 DOTATATE imaging in identifying the primary site in neuroendocrine tumors (NETS) of unknown primary, correlation of NET grade with median Standardized Uptake Value (SUV) and effects of long acting somatostatin analog on gallium-68 DOTATATE imaging quality needs to be evaluated. A single institution retrospective review of the first 200 NET patients with gallium-68 DOTATATE imaging from Dec 2016 to Dec 2017 was conducted. Questions related to NETs of unknown primary, correlation of Standardized Uptake Value (SUV) to Ki-67 (which signifies proliferation rate), the effects of long-acting systemic somatostatin analog (SSA) on SUV were part of our data analysis. From these 200 patients, 59.5% (119) were females, 40.5% (81) were males; the median age was 62 years. The following primary tumor sites were identified: small bowel-37.5%; pancreas-18.5%; bronchial-14%; colon-3.5%; rectum-2%; appendix-1.5%; adrenal-0.5%; prostate-0.5%; others-3% and unknown primary-19%. Mean hepatic SUV of the lesion with the greatest radiolabeled uptake in 96 patients was similar irrespective to exposure to long acting SSA. Patients exposed to long acting SSA had mean SUV of 31.3 vs 27.8 for SSA naïve patients. The difference was not statistically significant. Gallium-68 DOTATATE imaging seems to distinguished G3 NET from G1/G2 based on mean SUV, and also identified the primary tumor site in 17 of 38 (45%) patients with unknown primary. Systemic exposure to long acting SSA does not appear to influence mean SUV of gallium-68 DOTATATE scan.