ABSTRACT
In 1963, Gwilym S. Lodwick published the rst paper on computer-aided diagnosis of pulmonary nodules in chest radiographs (CXRs) (Lodwick et al., 1963). He described a system with over 50 features for a given nodule that described the lesion’s location, size, shape, and texture together with global features of the case at hand. ese data could be punched in a tabulator card for a machine prediction of the signicance of the nding. Lodwick wrote that “e built-in capacity to retain vast numbers of facts, to accept instruction from the physician to compare new facts with its stored information, to report the result of such comparison in the form of statistical probability, and to carry out these functions with great speed and accuracy makes the usefulness
of the computer most obvious.” Lodwick was a true pioneer of computer-aided diagnosis and coined the phrase for the rst time in 1966 (Lodwick, 1966). e rst paper to outline a complete computerized detection scheme was published by Ballard and Sklansky (1976), a result of the PhD work of Dana Ballard, who later published an authoritative textbook on computer vision (Ballard and Brown, 1982). is classic text is now available online (Ballard and Brown, 1982) and features many examples of image processing applied to CXRs.
