Deep learning for the detection of benign and malignant pulmonary nodules in non-screening chest CT scans.

BACKGROUND: Outside a screening program, early-stage lung cancer is generally diagnosed after the detection of incidental nodules in clinically ordered chest CT scans. Despite the advances in artificial intelligence (AI) systems for lung cancer detection, clinical validation of these systems is lacking in a non-screening setting. METHOD: We developed a deep learning-based AI system and assessed its performance for the detection of actionable benign nodules (requiring follow-up), small lung cancers, and pulmonary metastases in CT scans acquired in two Dutch hospitals (internal and external validation). A panel of five thoracic radiologists labeled all nodules, and two additional radiologists verified the nodule malignancy status and searched for any missed cancers using data from the national Netherlands Cancer Registry. The detection performance was evaluated by measuring the sensitivity at predefined false positive rates on a free receiver operating characteristic curve and was compared with the panel of radiologists. RESULTS: On the external test set (100 scans from 100 patients), the sensitivity of the AI system for detecting benign nodules, primary lung cancers, and metastases is respectively 94.3% (82/87, 95% CI: 88.1-98.8%), 96.9% (31/32, 95% CI: 91.7-100%), and 92.0% (104/113, 95% CI: 88.5-95.5%) at a clinically acceptable operating point of 1 false positive per scan (FP/s). These sensitivities are comparable to or higher than the radiologists, albeit with a slightly higher FP/s (average difference of 0.6). CONCLUSIONS: The AI system reliably detects benign and malignant pulmonary nodules in clinically indicated CT scans and can potentially assist radiologists in this setting.

Early-stage lung cancer can be diagnosed after identifying an abnormal spot on a chest CT scan ordered for other medical reasons. These spots or lung nodules can be overlooked by radiologists, as they are not necessarily the focus of an examination and can be as small as a few millimeters. Software using Artificial Intelligence (AI) technology has proven to be successful for aiding radiologists in this task, but its performance is understudied outside a lung cancer screening setting. We therefore developed and validated AI software for the detection of cancerous nodules or non-cancerous nodules that would need attention. We show that the software can reliably detect these nodules in a non-screening setting and could potentially aid radiologists in daily clinical practice.

Historical Review: The U.S. Army Medical Belt for Front Line First Aid: A Well-Considered Design That Failed the Medical Department During the First World War.

In December 1913, a board of medical officers was appointed to adapt new U.S. Army equipment to the needs of the Hospital Corps. One of the improvements concerned substitution of the satchel-like Hospital Corps pouch used to carry first aid equipment. A waist belt with 10 pockets, known as the medical belt, was devised, and supplied with a tourniquet, adhesive plaster, safety pins, iodine swabs, sublimated gauze, individual dressing packets, gauze bandages, aromatic spirit of ammonia, and common pins. In addition, an ax carrier accommodating a hand ax, a canteen hanger, and a pouch to carry diagnosis tags and instruments were attached to the medical belt. In 1916, the medical belt was incorporated in the field supply tables in the Manual for the Medical Department. The next year, on April 6, 1917, the U.S. Congress declared war on Germany in reaction to sinking of American ships by German submarines. Although the medical belt had given satisfaction in preliminary trials, it did not withstand the test of war. In practice, the medical belt proved a source of dissatisfaction both as to the methods of packing and its contents, which were considered useless in modern warfare. Subsequently, discontinuance of the medical belt was recommended.

[Hyperchloraemic metabolic acidosis in a patient with an ureteroileostomy according to Bricker]. / Hyperchloremische metabole acidose bij een patiënt met een brickerlis.

A 79-year-old male with a Bricker loop and chronic renal failure was admitted to hospital because progressive dyspnoea. This was due to severe hyperchloraemic metabolic acidosis. Hyperchloraemic acidosis can occur if urinary diversions are constructed from the colon or ileum. Contact between intestinal mucosa and urine may cause reabsorption of ammonium and chloride, and secretion of bicarbonate. Hyperchloraemic acidosis is rarely seen with an incontinent ileal loop due to its small absorbing surface area and the rapid drainage of urine from the loop. Hyperchloraemic acidosis in a patient with a Bricker loop may point to prolonged contact between the ileum and urine. A loopogram is necessary to investigate the cause. In our patient the loopogram showed that the incorporated bowel segment was too long. After shortening of the Bricker loop, the patient recovered from the hyperchloraemic metabolic acidosis.